Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Hongmin, Liao, Wenxiong, Liu, Zhengliang, Zhang, Yiyang, Huang, Xiaoke, Ding, Siqi, Ren, Hui, Wu, Zihao, Dai, Haixing, Li, Sheng, Wu, Lingfei, Liu, Ninghao, Li, Quanzheng, Liu, Tianming, Li, Xiang
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929235346587648
author Cai, Hongmin
Liao, Wenxiong
Liu, Zhengliang
Zhang, Yiyang
Huang, Xiaoke
Ding, Siqi
Ren, Hui
Wu, Zihao
Dai, Haixing
Li, Sheng
Wu, Lingfei
Liu, Ninghao
Li, Quanzheng
Liu, Tianming
Li, Xiang
author_facet Cai, Hongmin
Liao, Wenxiong
Liu, Zhengliang
Zhang, Yiyang
Huang, Xiaoke
Ding, Siqi
Ren, Hui
Wu, Zihao
Dai, Haixing
Li, Sheng
Wu, Lingfei
Liu, Ninghao
Li, Quanzheng
Liu, Tianming
Li, Xiang
contents Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs time-consuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domain-specific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.
format Preprint
id arxiv_https___arxiv_org_abs_2211_02849
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training
Cai, Hongmin
Liao, Wenxiong
Liu, Zhengliang
Zhang, Yiyang
Huang, Xiaoke
Ding, Siqi
Ren, Hui
Wu, Zihao
Dai, Haixing
Li, Sheng
Wu, Lingfei
Liu, Ninghao
Li, Quanzheng
Liu, Tianming
Li, Xiang
Artificial Intelligence
Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs time-consuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domain-specific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.
title Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training
topic Artificial Intelligence
url https://arxiv.org/abs/2211.02849